The Business Challenge
The business situation the organisation faced before the project began.
Fixed-time traffic signals follow preset schedules and may not respond well to changing traffic conditions. IntelliRoads evaluated an adaptive approach in SUMO simulation.
Why AI Was the Right Solution
Why AI was the right approach — and what alternatives were considered.
Traffic flow changes over time, while fixed-time schedules are predetermined. Reinforcement learning offered a way to evaluate signal decisions against changing simulated conditions before considering any real-world use.
How the Solution Was Delivered
Discovery, design, development, testing and rollout — the journey, not the tooling.
- 1Defined an adaptive traffic signal control problem and a fixed-time comparison baseline.
- 2Implemented a Double DQN controller and trained it in SUMO.
- 3Evaluated average waiting time against fixed-time control.
- 4Built a live dashboard and API integrations for the project.
Key Technical & Architecture Decisions
Architecture, model selection, workflow and trade-offs.
The project used SUMO as the simulation environment, Double DQN for adaptive signal control, and fixed-time control as the comparison baseline. A live dashboard and API integrations were built to inspect the system. The résumé does not specify further architecture details.
Challenges & How They Were Solved
Obstacles hit along the way and how they were overcome.
The available project notes do not describe specific implementation obstacles or how they were resolved, so no additional challenge claims are included in this draft.
Business Outcomes & Impact
The measurable outcomes recorded on this AI Case Study — with the story behind them.
In SUMO simulation, IntelliRoads reduced average waiting time by about 47% compared with fixed-time control. This is a simulation result, not a measurement from live roads.
Business Outcome Categories
The story behind the numbers
In SUMO simulation, average waiting time was reduced by about 47% compared with fixed-time control. This is a simulation result; it does not claim deployment on live roads or verified operational savings.
Lessons Learned
What surprised the team, what worked well, and what would be done differently.
- Keep the evaluation baseline explicit. Treat simulation improvements as evidence for further testing, not as proof of live-road impact.
Future Opportunities
Where this solution could go next.
A next step would be to test more traffic scenarios and demand patterns, report sample sizes and variability, and seek real-world validation before applying the approach to live roads.
Professional Reflections
Guidance for another builder tackling a similar problem.
The reported improvement is tied to a SUMO simulation and fixed-time baseline. Clear conditions and broader validation are needed before drawing conclusions about real-world impact.